Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2334 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.8176. Min Act: -0.1700
Data Index: 1091140 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.7551. Min Act: -0.1700
Data Index: 6364939 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.7238. Min Act: -0.1700
Data Index: 1998798 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.6301. Min Act: -0.1700
Data Index: 4706663 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.6301. Min Act: -0.1700
Data Index: 1258948 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.5676. Min Act: -0.1700
Data Index: 6415053 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.5676. Min Act: -0.1700
Data Index: 7908064 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.5363. Min Act: -0.1700
Data Index: 4297051 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.4426. Min Act: -0.1700
Data Index: 2066633 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.4113. Min Act: -0.1700
Data Index: 3276629 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.3801. Min Act: -0.1700
Data Index: 4698046 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.3488. Min Act: -0.1700
Data Index: 1357988 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.2551. Min Act: -0.1700
Data Index: 7555485 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.1926. Min Act: -0.1700
Data Index: 1129265 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.2238. Min Act: -0.1700
Data Index: 6175762 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.2238. Min Act: -0.1700
Data Index: 4286663 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.1613. Min Act: -0.1700
Data Index: 4105420 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.1613. Min Act: -0.1700
Data Index: 887344 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.1926. Min Act: -0.1700
Data Index: 6949234 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8176. Min Range: -7.8176
Max Act: 7.1613. Min Act: -0.1700
Data Index: 3911088 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19